Refresh this notebook with a small selection of source-backed developer growth and AI stories and LinkedIn drafts. Use for a requested content refresh, not arbitrary code changes or publishing to social networks.
90%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow has the agent search for and open arbitrary primary-source web pages (company, founder, practitioner, and research sources), which outsiders can publish to but cannot force into the workflow, so the risk is low.
fernandezbaptiste/baptiste-notebook
0d47c2b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.